SETUP.md

Setup and Recreation Guide

This document provides instructions on how to set up and recreate the Predictive Machine project locally without overwriting the README.md file (which is essential for Hugging Face Spaces).

Prerequisites

• Python 3.8 or higher
• pip (Python package manager)
• Git
• Docker (optional, for containerized deployment)

Local Setup

1. Clone the Repository

git clone https://huggingface.co/spaces/Asah-ML-Copilot-A25-CS047/Predictive-Machine
cd Predictive-Machine

2. Create a Virtual Environment

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install Dependencies

pip install -r requirements.txt

4. Download the Dataset

The project uses the Kaggle dataset: Machine Predictive Maintenance Classification

• Download the dataset from Kaggle
• Extract it to a data/ directory in the project root
• Or set up Kaggle API credentials:

pip install kaggle
kaggle datasets download -d shivamb/machine-predictive-maintenance-classification
unzip machine-predictive-maintenance-classification.zip -d data/

5. Run the Application

uvicorn app:app --reload

Preserving README.md for Hugging Face Spaces

Important: The README.md file contains critical Hugging Face Spaces configuration metadata (YAML front matter). When updating the project:

1. Never overwrite or delete README.md

2. Keep the YAML header intact: ```yaml

   title: Predictive Machine emoji: 🚨 colorFrom: pink colorTo: indigo sdk: docker pinned: true license: apache-2.0 short_description: Predictive Machine Copilot for Asah by Dicoding x Accenture datasets: [https://www.kaggle.com/datasets/shivamb/machine-predictive-maintenance-classification/data]

3. Use this SETUP.md file for development documentation instead
4. If you need to update README.md content, only modify the area AFTER the closing ---

Docker Deployment

Build the Docker Image

docker build -t predictive-machine .

Run the Container

docker run -p 7860:7860 predictive-machine

The application will be available at http://localhost:7860

Project Structure

Predictive-Machine/
├── README.md              # Hugging Face Spaces config (DO NOT OVERWRITE)
├── SETUP.md              # This file - local setup instructions
├── Dockerfile            # Docker configuration
├── requirements.txt      # Python dependencies
├── app.py               # Main application
├── data/                # Dataset directory
├── models/              # Trained models
└── src/                 # Source code modules

Development Workflow

1. Create a new branch for features:

   git checkout -b feature/your-feature-name
   

2. Make changes and test locally

3. Commit and push changes:

   git add .
   git commit -m "Description of changes"
   git push origin feature/your-feature-name
   

4. Create a pull request

5. Once merged, the changes will be reflected in the Hugging Face Spaces deployment

Troubleshooting

Dataset Download Issues

• Ensure you have Kaggle API credentials configured: ~/.kaggle/kaggle.json
• Or download manually from Kaggle and place files in data/ directory

Dependency Conflicts

pip install --upgrade pip
pip install -r requirements.txt --force-reinstall

Docker Build Issues

docker build --no-cache -t predictive-machine .

License

This project is licensed under the Apache 2.0 License - see LICENSE file for details.

Resources

• Hugging Face Spaces Documentation
• Hugging Face Spaces Config Reference
• Dataset: Machine Predictive Maintenance Classification